Deep Reinforcement Learning for Hybrid RIS Assisted MIMO Communications

TL;DR

This paper introduces a DRL-based approach to optimize hybrid RIS-assisted MIMO systems, achieving near-optimal spectral efficiency with reduced computational complexity.

Contribution

It presents a novel deep reinforcement learning framework that directly maps channel information to optimal configurations, overcoming the computational challenges of traditional methods.

Findings

DRL method achieves 95% of benchmark spectral efficiency.

Significantly reduces computational complexity compared to iterative solutions.

Trained offline, enabling low-latency real-time configuration.

Abstract

Hybrid reconfigurable intelligent surfaces (HRIS) enhance wireless systems by combining passive reflection with active signal amplification. However, jointly optimizing the transmit beamforming with the HRIS reflection and amplification coefficients to maximize spectral efficiency (SE) is a non-convex problem, and conventional iterative solutions are computationally intensive. To address this, we propose a deep reinforcement learning (DRL) framework that learns a direct mapping from channel state information to the near-optimal transmit beamforming and HRIS configurations. The DRL model is trained offline, after which it can compute the beamforming and HRIS configurations with low complexity and latency. Simulation results demonstrate that our DRL-based method achieves 95% of the SE obtained by the alternating optimization benchmark, while significantly lowering the computational complexity.